Productivity

serac-labs Skill

Build ServiceNow Knowledge Management — kb_knowledge articles, draft/review/published workflow, kb_category placement, full-text search with snippets, article templates, and kb_feedback rating rollup.

xu-jin-cs Bundle

ppt 主链 Gate A（设计决策出口，2026-08-15 裁定自归档 legacy-workflow 引擎迁移 gate-switch）：主线06 质检通过后、主线07 渲染入参组装前扳动。

xu-jin-cs Bundle

并行调度与子分身机制总规则（2026-08-14 用户裁定正式版；2026-08-16 增补 PARALLEL-GATE 门禁与文件数量纲）。只要出现多任务（≥2 个子任务/诉求）即强制触发并行判定并输出 [PARALLEL-GATE] 声明，无触发词依赖；任务拆解产生 ≥2 个无依赖子任务时默认主动并行 spawn 子分身，只评估不执行视为故意串行化。量纲唯一化：任务量只用文件数量评估（禁用小时/体感）。双维决策：规模轴（≤3文件→轻分身 / >3文件或契约耦合→task_breakdown 定档 / >10文件且M/L→引擎级分身）× 数量轴（2~5→subagent 扇出 / 6~9→分组扇出 / ≥10 或批量同类→workflow 编排）。含三槽契约（PRE-SPAWN/RECEIPT/MERGE）、最小探针、母体合并校验、时点分层、禁止清单。

xu-jin-cs Bundle

多智能体工作流治理规则包：目录安全铁律、流程A/B/C 全流程、任务路由。

allemaar Bundle

Propose a phased, gated implementation plan before any work begins. Trigger when the user runs /plan-create, says "make a plan", "plan this out", "design before coding", "let's plan first", "architect this", or asks for a phased approach before implementation. Also trigger proactively when a task is complex enough that jumping straight to execution would be risky — multi-file changes, new features, architectural shifts, refactors spanning multiple components, or any task where misalignment early would be expensive to fix later. Output: a structured PLAN.md with phases, changes, risks, and verification criteria. Design only — no implementation code is written during /plan-create. Use plan-phases to restructure an existing plan, plan-execute to run an approved plan, plan-deep-dive to inspect a plan, plan-evolve to evolve shipped work, and plan-cleanup after execution.

borda Skill

Analysis-only planning — classify and scope a task without writing code; outputs a structured plan to .plans/active/. TRIGGER when: user wants to understand scope and risks before implementation; phrases: "plan this", "scope out X", "what would it take to Y", "analyse before we start". SKIP when: user already knows what to build and wants code immediately (use `/develop:feature` or `/develop:fix` directly); `.claude/` config planning (use `/foundry:manage`).

borda Bundle

Implement changes with a linear plan-build-verify workflow and measurable quality gates.

epicenterhq Skill

Shape a complex idea, workflow, or design into the smallest complete surface a person needs for the next judgment.

allemaar Bundle

Multi-pass adversarial critique from dynamically selected personas — including Claude's own POV. Trigger on: "adversarial", "red team this", "multi-POV review", "stress-test", "poke holes", "what am I missing", "attack my plan", "critique from multiple angles", "is this solid", "what would a skeptic say", or any request for rigorous structured criticism of a plan, design, doc, workflow, YON, idea, or system. Runs 1–3 passes. First pass selects 4+ personas from the roster. Each subsequent pass adds 2–4 new personas to the mix. Third pass wraps with a final verdict if all issues are within acceptable params. Do not skip this skill when the user wants real scrutiny — "just give me feedback" often means they need this.

ci Bundle

Full autonomous engineering workflow

heyeddi-com Bundle

Traces user task flows with Playwright: click depth, step success, friction: and writes reports to .heyeddi/docs/ux-flows/. Use when measuring ease of use, clicks to complete a task, or onboarding friction. Not for static visual critique (use heyeddi-design critique) or layout screenshots (use visual-auditor).

heyeddi-com Bundle

Implements Flutter screens from designer screenshots and handoff notes using Material 3. Two-pass workflow: mockup-brief with Implementation spec, then AppShell + route screens. Use when approved mockups exist for a HeyEddi Flutter app.

zyrexnn Skill

Hunt Missing/Weak Rate Limiting — login brute force, OTP/2FA brute force (10^6 keyspace), password-reset-token brute, credential stuffing, username/email enumeration via error-string / status-code / timing differences, weak password policy, missing CAPTCHA (CAPTCHA token replay / single-use / concurrency-window bypass specifics → hunt-captcha-bypass), IP-based rate-limit bypass via X-Forwarded-For and friends, ReDoS. Distinguishes hard lockout vs soft IP-throttle vs CAPTCHA-injection vs silent shadow-throttling (avoids false-negative 'no rate limit' conclusions). Medium to Critical depending on what the brute reaches (OTP→ATO = Critical).

zyrexnn Skill

Hunt TLS/SSL and DNS misconfigurations — missing HSTS (downgrade attack), weak cipher suites, expired/invalid certificates, mTLS bypass, missing SPF/DKIM/DMARC (email spoofing), DNS Zone Transfer (AXFR), dangling CNAME subdomain takeover, CAA records. Most of these are Info/Low on their own — this skill is opinionated about which findings actually pay (spoofable DMARC with delivered-to-inbox proof, AXFR returning internal hosts, dangling-CNAME takeover) versus which get rejected as best-practice noise (missing CAA, missing HSTS with no MitM position). Use during recon to find infrastructure weaknesses, and to TRIAGE them honestly before reporting.

leoyishou Bundle

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

zouyangxiaohao111 Bundle

Use when you have a spec or requirements for a multi-step task, before touching code

zouyangxiaohao111 Skill

Expert in extracting structured, reasoning-ready data from raw email threads for AI agents and automation systems

applicate2628 Bundle

Use when a Git repository moves machines without losing dirty work, ignored task memory, or local runtime evidence.

postpartum-genushyacinthus29 Bundle

Adopt MCAF governance in a .NET repository with the right AGENTS.md layout, repo-native docs, skill installation, verification rules, and non-trivial task workflow. Use when bootstrapping or updating MCAF alongside the dotnet-skills catalog.

practice019 Skill

在 DSH 中创建、校验、安装和发布本地 Skill 的完整协议与流程。涵盖 SKILL.md frontmatter 规范、命名规则、YAML 安全写法、路径引用规范（禁 ~ / 禁机器绝对路径）、目录位置、校验方法、常见踩坑（冒号空格/CRLF/引号）以及用 skill 工具加载验证与 available_skills 观察法。当用户想新建一个 skill、把流程沉淀为 skill、修复无法被 DSH 扫描到的 skill 时使用本技能。Create, validate, install, and publish local DSH Skills: SKILL.md frontmatter spec, kebab-case naming, YAML-safe quoting, path reference rules, directory layout, validation commands, and the common traps that make a skill silently unscannable. Use when the user wants to build a new skill, turn a workflow into a skill, or fix a skill DSH cannot load.

practice019 Skill

用 uv + ruff + pyright 搭建现代 Python 项目：初始化、依赖管理、环境配置、lint 与格式化。当用户要新建 Python 项目、配置 uv、设置 lint/format 时使用。 Modern Python project setup with uv, ruff, and pyright. Use when initializing a new Python project, configuring the Python environment, setting up linting/formatting, or when a project needs uv (the fast Python package manager). Trigger on: 'set up Python', 'new Python project', 'configure uv', 'install uv', 'ruff', 'pyright', 'Python linting', 'Python formatting', or when a task requires Python and no pyproject.toml exists yet.

practice019 Skill

把用户的粗略想法对齐成可执行的事：共同判断是「当前会话顺手做掉」还是「固化成正式 Task（在 .task/ 下产出四份文档后独立派发）」。当用户描述一个想先对齐再动手的任务或意图时使用：帮我规划一下、先理一理、我想探索 X、我有个想法、/task-alignment；用户没定义范围或验收标准就直接跳进复杂任务时，也应主动暂停并对齐。 Alignment conversation starting from a user's rough idea. Co-decides with the user whether the idea should be acted on directly in the current session, or fixed into a formal Task by producing four documents in `.task/` for independent dispatch. Handles lightweight 'do it now while we talk', heavyweight 'define precisely, run later', and 'just help me think about this' — all on the same skill. Use when the user describes a task or intent they want to align on. Trigger phrases include 'help me plan this', 'let's think this through', 'I want to explore X', 'I have an idea', '/task-alignment'. Also use proactively when a user jumps into a complex task without defining scope or success criteria — pause, align, and help them pick the right vessel (this session vs. a task).

practice019 Skill

作为用户代理自主执行已对齐的任务：读取任务文档定目标、拆解工作、按需委派子智能体、由独立主体校验后交付。当工作空间已有 .task 任务目录且用户要开始执行时使用；触发指令 /task-implement、/task-implement <slug>、start the task、go ahead and implement、execute the plan，或用户确认对齐文档后说「没问题，开始执行」。Autonomously run a planned task as the user's proxy: read the task brief, decompose the work, delegate to subagents, verify independently, and deliver. Use for /task-implement, start the task, go ahead and implement, or execute the plan.

practice019 Bundle

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for ZIP and PKZIP archive challenges, legacy ZipCrypto identification, known-plaintext recovery with bkcrack, key-based decryption, and reproducible extraction. Use when the user asks to solve an encrypted ZIP challenge, inspect ZipCrypto metadata, recover keys from a known file prefix, or unlock an archive without starting with password brute force. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

arnie016 Bundle

Design repeatable fan rituals, naming systems, participation loops, and recurring community formats, then output a ritual calendar. Use when Codex needs to turn audience energy into recurring formats without making the relationship manipulative or exhausting.

arnie016 Bundle

Build, run, troubleshoot, or refine the native On This Day Bar macOS menu bar app in `apps/on-this-day-bar`. Use when Codex needs to work on the daily history bar app, regenerate the XcodeGen project, run doctor/build/test checks, or improve the compact cached-feed menu bar workflow.

arnie016 Bundle

Build, scaffold, troubleshoot, or product-shape a macOS rescue launcher, focus ritual, or last-minute shipping workflow that can start a hype song, open critical apps and docs, start a countdown, and copy a heads-down status update. Use when Codex needs to turn "Project Hail Mary", "panic mode", or "play Sign of the Times and open everything I need" into a realistic menu bar app, shortcut, script, or launch sequence without inventing unsupported music or messaging APIs.

arnie016 Bundle

Build or operate a macOS menu-bar Chrome tab control surface that lists overloaded browser tabs, groups them by domain or task, and closes explicit selected tab batches with a safe review step.

arnie016 Bundle

Build or operate a macOS menu-bar bridge that turns the current meeting join link into a clean handoff for notes, chat, email, or a fast open action, with extra weight for Microsoft Teams and browser-based meeting flows.

arnie016 Bundle

A device handoff panel for opening your phone, jump-starting a task, and keeping the Mac in the loop.

arnie016 Bundle

Build, run, troubleshoot, or refine a realistic Mac phone-recovery workflow, especially the bundled `apps/phone-spotter` menu bar app. Use when Codex needs a repo-native path for locate, ring, call, pairing, directions, or provider handoff on iPhone or Android without inventing unsupported tracking APIs.

arnie016 Bundle

Draft, clean, preview, register, or build a Minecraft Java skin workflow, including the bundled `apps/minecraft-skinbar` menu bar app. Use when Codex needs to turn a skin idea into launcher-ready files, wire the local Minecraft Launcher skin library, render previews, or refine the repo-native macOS skin workflow.

halseyyang Skill

Use when the user asks for OpenSpec, spec-driven development, SDD, OPSX commands, product/engineering proposals, requirements/spec changes, implementation plans tied to specs, validating implementation against specs, or archiving completed changes. Provides workflow guidance for Fission-AI OpenSpec and the installed `openspec` CLI.

halseyyang Bundle

Medical device risk management workflow for ISO 14971-style hazard analysis, risk controls, benefit-risk reasoning, residual risk evaluation, and risk-management file preparation.

cdeistopened Skill

Extract a writer's voice from their archive, produce a reusable voice fingerprint, then write in that voice with calibration. Two modes — EXTRACT (analyze samples → produce fingerprint) and WRITE (use fingerprint → produce content). For any writing task involving Charlie's voice, skip to the Charlie Deist Fingerprint section. For extracting anyone's voice, start at Phase 1.

cdeistopened Bundle

Instagram competitive intelligence and content strategy tool. Scrapes competitor profiles via Apify, detects trending content across Instagram/TikTok/Google Trends, analyzes viral posts with Gemini AI, and generates creative briefs adapted to any creator's voice and brand. Use this skill whenever the user mentions Instagram content strategy, competitor analysis, social media trend scouting, content calendar planning, viral post analysis, creative briefs, or wants to understand what's performing well on Instagram in a niche — even if they don't explicitly say "instagram-scout."